FSscore: A Personalized Machine Learning‐Based Synthetic Feasibility Score
Chemistry–Methods · 2024-11 · 4 (11)
DOI: 10.1002/cmtd.202400024 ↗Kurz gefasst
Fachartikel in der Zeitschrift Chemistry–Methods, online erschienen am 18.10.2024. Verfasst von Rebecca M. Neeser und 2 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NCCR Catalysis.
Abstract (Originalsprache)
Determining whether a molecule can be synthesized is crucial in chemistry and drug discovery, as it guides experimental prioritization and molecule ranking in de novo design tasks. Existing scoring approaches to assess synthetic feasibility struggle to extrapolate to new chemical spaces or fail to discriminate based on subtle differences such as chirality. This work addresses these limitations by introducing the Focused Synthesizability score (FSscore), which uses machine learning to rank structures based on their relative ease of synthesis. First, a baseline trained on an extensive set of reactant‐product pairs is established, which is then refined with expert human feedback tailored to specific chemical spaces. This targeted fine‐tuning improves performance on these chemical scopes, enabling more accurate differentiation between molecules that are hard and easy to synthesize. The FSscore showcases how a human‐in‐the‐loop framework can be utilized to optimize the assessment of synthetic feasibility for various chemical applications.
Förderung
- NCCR Catalysis
Zitieren
APA
Neeser, R. M., Correia, B., & Schwaller, P. (2024). FSscore: A Personalized Machine Learning‐Based Synthetic Feasibility Score. Chemistry–Methods, 4(11). https://doi.org/10.1002/cmtd.202400024
Vancouver
Neeser RM, Correia B, Schwaller P. FSscore: A Personalized Machine Learning‐Based Synthetic Feasibility Score. Chemistry–Methods. 2024;4(11). doi:10.1002/cmtd.202400024
BibTeX
@article{Neeser2024,
author = {Neeser, Rebecca M. and Correia, Bruno and Schwaller, Philippe},
title = {FSscore: A Personalized Machine Learning‐Based Synthetic Feasibility Score},
journal = {Chemistry–Methods},
year = {2024},
volume = {4},
number = {11},
doi = {10.1002/cmtd.202400024}
}
EUVIMED